syncrope/cascadia-selectors-level4

Task gallery / DeepSWE (long-horizon SWE) / Version 1

Reference solution (oracle): Unverified
No-op resistance check: Unverified
QA verdict: Not recorded
Aggregate eligibility: Eligible version

The task

cascadia (github.com/andybalholm/cascadia), the CSS selector engine for Go's x/net/html trees, still speaks Selectors Level 3 plus nonstandard extensions. Upgrade it to the selector-matching core of W3C Selectors Level 4; the 22 January 2026 Working Draft settles every semantic question this note leaves open. Everything is reachable through the existing public API (Parse, ParseWithPseudoElement, ParseGroup, ParseGro…

Excerpt only; not a complete executable task specification. Task ID task_28206617bb4d469a · version 1. Selection status: not fully recorded.

Results by model and effort

This exact task version only. Every rate is passes / valid runs with a Wilson 95% interval; n≤2 remains counts only. Macro aggregation does not apply within a single task. Baselines are summarized in the quality gates, not ranked. A passed no-op resistance check means that doing nothing did not solve the task.

Current evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes

Legacy evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes
Claude Opus 4.8 · default (unverified)	0/5 · 0.0% [0.0%, 43.4%]	5 / 5	0	GOOD_FAILURE: 5 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0

Every recorded run

5 recorded trials, including controls. Diagnostic labels do not replace verifier reward. Labels and quality checks are source declarations, not independently attested here. Internal evidence remains private; a missing public URL is shown explicitly. Records with invalid or absent rewards are not scored.

Run / model	Date / source	Reward / eligibility	Diagnostic class / source	Resources	Evidence
`trial_34c6b9d8cb534d55` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 91,828 Turns: 66 Cost: $7.4646	Not publicly available
`trial_43183a5fadb84e28` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 80,937 Turns: 59 Cost: $6.5538	Not publicly available
`trial_544af106811048fe` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 84,631 Turns: 57 Cost: $6.5440	Not publicly available
`trial_60087742022d4e73` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 107,581 Turns: 69 Cost: $8.8214	Not publicly available
`trial_be5003982865445d` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 83,172 Turns: 56 Cost: $6.5544	Not publicly available